SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 04825 · ECCV · 2024

Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging

Xin Yuan, Ying Fu, Zongliang Wu, Ruiying Lu

Open in the Atlas

Code that ran

4 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/04825.json · badge: /api/ran/04825.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
Zongliang-Wu/LADE-DUN canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
A Ran
ran on a synthesized input
Zongliang-Wu/LADE-DUN/train_code_real/architecture/dun_utils.py
code served (permissive licence) · get_code("588b2fb6f6e02e2e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 3, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# x: shape (B, nC, H, W) - a 4D tensor
# The function multiplies x by Phi, sums over dimension 1 (nC),
# and divides by nC and multiplies by 2
B, nC, H, W = 2, 4, 3, 5
x = torch.randn(B, nC, H, W)

# Phi: must be broadcastable with x for element-wise multiplication
# Looking at the operation: temp = x * Phi
# Phi should have shape compatible with (B, nC, H, W)
# Most likely shape is (B, nC, H, W) or (nC, H, W) or similar
Phi = torch.randn(B, nC, H, W)

ARGS = {
    "x": x,
    "Phi": Phi
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 3, 5) — shape (2, 3, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_cosine_schedule_with_warmup Ran
ran on a synthesized input
Zongliang-Wu/LADE-DUN/train_code_real/schedulers.py
code served (permissive licence) · get_code("2c6be7bea93f6921")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned LambdaLR. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from torch.optim import Adam

torch.manual_seed(0)

# Create a minimal model with parameters
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = Adam(model.parameters(), lr=0.001)

# Define arguments for get_cosine_schedule_with_warmup
ARGS = {
    "optimizer": optimizer,
    "num_warmup_steps": 100,
    "num_training_steps": 1000,
    "num_cycles": 0.5,
    "last_epoch": -1,
    "eta_min": 1e-06
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
merge_network_opt Ran
ran on a synthesized input
Zongliang-Wu/LADE-DUN/train_code_real/options/network_option.py
code served (permissive licence) · get_code("4bef4136d8ed9848")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ArgumentParser. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import argparse

torch.manual_seed(0)

ARGS = {
    'parser': argparse.ArgumentParser()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArgumentParser — a ArgumentParser output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ArgumentParser output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
shift_3d Ran
ran on a synthesized input
Zongliang-Wu/LADE-DUN/train_code_real/architecture/dun_utils.py
code served (permissive licence) · get_code("41f9d5f2140e43a7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 3, 11) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small 4D input tensor: [batch_size, channels, height, width]
# Using distinct sizes: bs=2, nC=4, row=3, col=5
inputs = torch.randn(2, 4, 3, 5)

# step parameter
step = 2

ARGS = {
    "inputs": inputs,
    "step": step,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 4, 3, 11) — shape (2, 4, 3, 11) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
At Not yet run
unverified (harvested, no recorded run)
Zongliang-Wu/LADE-DUN/train_code_real/architecture/dun_utils.py
code served (permissive licence) · get_code("55acb8b60fa27c7e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
At 1 other paper
1 dated earlier
2205.10102 (2022-05)
Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Snapshot compressive spectral imaging reconstruction aims to reconstruct three-dimensional spatial-spectral images from a singleshot two-dimensional compressed measurement. Existing state-of-the-art methods are mostly based on deep unfolding structures but have intrinsic performance bottlenecks: i) the ill-posed problem of dealing with heavily degraded measurement, and ii) the regression loss-based reconstruction models being prone to recover images with few details. In this paper, we introduce a generative model, namely the latent diffusion model (LDM), to generate degradation-free prior to enhance the regression-based deep unfolding method by a two-stage training procedure. Furthermore, we propose a Trident Transformer (TT), which extracts correlations among prior knowledge, spatial, and spectral features, to integrate knowledge priors in deep unfolding denoiser, and guide the reconstruction for compensating high-quality spectral signal details. To our knowledge, this is the first approach to integrate physics-driven deep unfolding with generative LDM in the context of CASSI reconstruction. Comparisons on synthetic and real-world datasets illustrate the superiority of our proposed method in both reconstruction quality and computational efficiency. The code is available at https://github.com/Zongliang-Wu/LADE-DUN.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("04825")
get_code_for_paper("04825")
have("04825")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/04825.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/04825.svg)](https://syntology.ai/paper/04825)

Connect an agent — have() is free.